{"total":48,"rows":[{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2102.01229","title":"Doubly robust Thompson sampling for linear payoffs","created":"2021-02-01","cited_by_count":21,"area":null},{"id":"2102.09626","title":"A Simple Unified Framework for High Dimensional Bandit Problems","created":"2021-02-18","cited_by_count":21,"area":null},{"id":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2210.15345","title":"PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits","created":"2022-10-25","cited_by_count":17,"area":null},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2211.05964","title":"Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits","created":"2022-11-11","cited_by_count":16,"area":null},{"id":"2209.06983","title":"Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2109.11612","title":"Regret Lower Bound and Optimal Algorithm for High-Dimensional Contextual Linear Bandit","created":"2021-09-23","cited_by_count":8,"area":null},{"id":"2309.08634","title":"Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2306.06291","title":"Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2206.05404","title":"Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits","created":"2022-06-11","cited_by_count":6,"area":null},{"id":"2307.12897","title":"Anytime Model Selection in Linear Bandits","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2506.12751","title":"Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions","created":"2025-06-15","cited_by_count":6,"area":null},{"id":"2202.00602","title":"Meta-Learning Hypothesis Spaces for Sequential Decision-making","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2210.06719","title":"Reward Imputation with Sketching for Contextual Batched Bandits","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2306.11017","title":"High-dimensional Contextual Bandit Problem without Sparsity","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2502.06142","title":"Linear Bandits with Partially Observable Features","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2605.10405","title":"Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2202.13448","title":"Federated Online Sparse Decision Making","created":"2022-02-27","cited_by_count":3,"area":null},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2310.15286","title":"A Doubly Robust Approach to Sparse Reinforcement Learning","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2311.01327","title":"High-dimensional Linear Bandits with Knapsacks","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2207.11165","title":"High dimensional stochastic linear contextual bandit with missing covariates","created":"2022-07-22","cited_by_count":2,"area":null},{"id":"2301.13791","title":"Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2404.17592","title":"Low-Rank Online Dynamic Assortment with Dual Contextual Information","created":"2024-04-19","cited_by_count":2,"area":null},{"id":"2209.08403","title":"Advertising Media and Target Audience Optimization via High-dimensional Bandits","created":"2022-09-17","cited_by_count":1,"area":null},{"id":"2302.00814","title":"Stochastic Contextual Bandits with Long Horizon Rewards","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2311.00481","title":"Fixed-Budget Best-Arm Identification in Sparse Linear Bandits","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2312.12400","title":"New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem","created":"2023-12-19","cited_by_count":1,"area":null},{"id":"2405.13899","title":"Symmetric Linear Bandits with Hidden Symmetry","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2405.14038","title":"FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2501.10722","title":"A Unified Regularization Approach to High-Dimensional Generalized Tensor Bandits","created":"2025-01-18","cited_by_count":1,"area":null},{"id":"2505.14102","title":"High-dimensional Nonparametric Contextual Bandit Problem","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2510.24234","title":"Sparse Optimistic Information Directed Sampling","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2202.03167","title":"Bayesian Non-stationary Linear Bandits for Large-Scale Recommender Systems","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2211.08311","title":"On Penalization in Stochastic Multi-armed Bandits","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2305.19161","title":"Cooperative Thresholded Lasso for Sparse Linear Bandit","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2409.09199","title":"Batched Online Contextual Sparse Bandits with Sequential Inclusion of Features","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2410.20041","title":"Sparse Linear Bandits with Blocking Constraints","created":"2024-10-26","cited_by_count":0,"area":null},{"id":"2503.16382","title":"Sparse Nonparametric Contextual Bandits","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2506.14479","title":"Adaptive Data Augmentation for Thompson Sampling","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2510.08435","title":"Navigating Sparsities in High-Dimensional Linear Contextual Bandits","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2605.10151","title":"Learning to Sparsify Stochastic Linear Bandits","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27794","title":"Learning to target with network interference","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}